© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19172
    Prev
    Next
    INDEX
    Explanations

    specific string formats or sequences in data structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.87
    Hochspringen
    -0.84
    存于互联网档案馆
    -0.82
     odkazy
    -0.81
    XmlAccessType
    -0.80
    richTextPanel
    -0.79
     الاطلاع
    -0.79
    IntoConstraints
    -0.79
    GEBURTSDATUM
    -0.75
     CreateTagHelper
    -0.74
    POSITIVE LOGITS
    собенности
    0.65
    unis
    0.55
    ύπ
    0.55
    стоит
    0.55
     bebas
    0.54
     collège
    0.54
     Gon
    0.53
    Gon
    0.52
    brigens
    0.51
    ecé
    0.51
    Activations Density 0.028%

    No Known Activations